利用dataset数据集进行卷积
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader
dataset_transform = torchvision.transforms.Compose([
torchvision.transforms.ToTensor()
])
获取数据集（标准数据集）
test_data = torchvision.datasets.CIFAR10(root=“PointCloud_data/data_3”, train=False,
transform=dataset_transform, download=True)
加载数据
test_loader = DataLoader(dataset=test_data, batch_size=4, shuffle=True, num_workers=0, drop_last=False)
搭载神经网络：对数据集进行操作
class Tudui(nn.Module):
def int(self):
super(Tudui, self).int()
self.conv1 = Conv2d(in_channels=3, out_channels=6, kernel_size=3, stride=1, padding=0)
def forward(self, _input):
_output = self.conv1(_input) # x输入到该卷积层
return _output
声明类
tudui = Tudui()
for data in test_loader:
imgs, targets = data
output = tudui(imgs)
print(imgs.shape)